AF self-evolution
Autonomous self-improvement engine that learns from interactions, identifies patterns, and evolves behavior over time. Use when: (1) Analyzing interaction patterns for improvement, (2) Running periodic self-assessment, (3) Extracting reusable patterns from workflows, (4) Optimizing decision-making processes, (5) Integrating feedback into behavioral changes. Triggers on '自我进化', 'self-evolution', '自我改进', '学习模式', 'pattern analysis', 'optimize behavior'.
As a process F 41/100 · Will not run — References files that are not bundled: scripts/detectors/
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/detectors/
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: scripts/detectors/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (self-evolution) differs from the folder (self-evolution-engine)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 43 steps
- 100Execution cost. Instruction body is 2659 tokens
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 454: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (25 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.